def test_klass():
dset = Dataset()
# dset.add(dset.load_emojis())
dset.add(dset.tm_words())
kl = dset.klasses
xx = dset.klass("xxx good xxx morning xxT")
for k in xx:
assert k in kl
def test_add():
dset = Dataset()
assert len(dset.klasses) == 0
dset.add(dset.load_emojis())
cnt = len(dset.klasses)
assert cnt > 0
words = dset.tm_words()
dset.add(words)
print(len(dset.klasses), len(words), cnt)
assert len(dset.klasses) <= len(words) + cnt
def test_remove():
dset = Dataset()
dset.add(dset.load_emojis())
dset.add(dset.tm_words())
xx = dset.klass("xxx good morning xxx asdfa")
print(xx)
assert len(xx) == 2
dset.remove("~good~")
xx = dset.klass("xxx good xxx morning xxx")
print(xx)
assert len(xx) == 1
def test_process():
from microtc.emoticons import convert_emoji
dset = Dataset()
dset.add(dset.load_emojis())
dset.add(dset.tm_words())
xx = dset.process("xxx good 9 morning xxx fax x la", "~x~")
for a, b in zip(xx, ["~xxx~good~9~morning~xxx~fax~", "~la~", "~la~"]):
print(a, b)
assert a == b
txt = 'xxx good {} morning xxx fax x la'.format(convert_emoji('1F600'))
xx = dset.process(txt, convert_emoji('1F600'))
print(xx)
for a, b in zip(xx, ["~xxx~good~", "~morning~xxx~fax~x~la~"]):
assert a == b